Finite-dimensional linear minimization is no slower than projection
Statement
Let be the Hilbert space underlying the compact convex set considered, and let denote the optimal runtime complexity of its projection operator, while denotes the optimal runtime complexity of exact linear minimization. Finite-dimensional complexity claim. If the dimension of is finite, then
This establishes that exact linear minimization is no slower than projection up to a constant factor in finite-dimensional spaces. The surrounding discussion notes that the general relationship between and warrants further investigation, including whether some compact convex set could satisfy ; the supplied text does not state whether this finite-dimensional claim has been proved.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.